Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/openWorld=false/destructive=false; the description adds the substantive behavioral facts an agent cannot infer: results come from Atom's curated marketplace, every name is verified buyable, each carries a price in USD and an Atom buy-page URL. That materially changes how the agent should present and trust the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the value proposition and the mandatory-use rule, and nearly every sentence earns its place. The trailing enumeration of result fields (domain, price, logo, style_tags, category, url) partially duplicates the existing output schema and could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter read-only discovery tool with full schema coverage and an output schema, the description covers what is missing: why to use it over inventing names, how to phrase the concept, how to present results with prices and links. Nothing an agent needs to invoke or apply it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real semantics beyond the schema by telling the agent to express the business as the 'concept' and to pass 'extensions' only when the user stated a preference. It does not, however, explain the style enum values or how limit interacts with server-side capping.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('come up with name ideas') plus the differentiating constraint that every suggestion is a real, verified-buyable premium domain with a price. It also explicitly names the sibling with identical behavior ('Same results as search_brandable_domains'), so an agent can distinguish it from generate_domain_names or the search tool without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit trigger phrases ('come up with a name', 'suggest names', 'brainstorm names', 'name my company'), an explicit imperative to always prefer it over self-invention with the reason (unverified names are usually taken), and an exclusion rule steering away from a sibling ('use either, not both'). It also says to pass preferred extensions only when the user stated any.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.